Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :h
    -0.07
     Am
    -0.06
    uded
    -0.06
     searchText
    -0.06
     her
    -0.06
     herself
    -0.06
     Helps
    -0.06
     himself
    -0.06
    (Utils
    -0.06
     hundreds
    -0.06
    POSITIVE LOGITS
     LogManager
    0.07
    orthand
    0.06
    piar
    0.06
    ||(
    0.06
    istant
    0.06
    天天
    0.06
     معل
    0.06
    orge
    0.06
    ensburg
    0.06
    >>(
    0.06
    Act Density 0.164%

    No Known Activations